UMass amherst Engineers Develop Artificial Neuron Mirroring human Brain Efficiency
Table of Contents
A groundbreaking innovation from the University of Massachusetts Amherst promises too revolutionize computing with an artificial neuron that replicates the energy efficiency of its biological counterpart. The development, detailed in a recent study published in Nature Communications, could pave the way for computers that consume dramatically less power and even interface directly with the human body.
The quest for energy-efficient computing has long been hampered by the high voltage requirements of traditional artificial neurons. However, researchers have overcome this obstacle by leveraging the unique properties of protein nanowires derived from electricity-producing bacteria. This breakthrough represents a important step toward bio-inspired computing and a potential solution to the escalating energy demands of modern technology.
The Brain’s Efficiency: A Benchmark for Computing
The human brain is a marvel of efficiency. Despite processing an enormous amount of data, it operates on remarkably low power – approximately 20 watts when performing a complex task like writing. In stark contrast, a Large Language Model such as ChatGPT can require over a megawatt to achieve the same result. this disparity highlights the vast potential for enhancement in current computer systems.
“Our brain processes an enormous amount of data,” explains a graduate student in electrical and computer engineering at umass Amherst and lead author of the study. “But its power usage is very, very low, especially compared to the amount of electricity it takes to run a Large Language Model, like ChatGPT.”
The human body, as a whole, operates with electrical efficiency exceeding that of typical computer circuits by a factor of over 100. This efficiency stems from the billions of specialized cells – neurons – that transmit electrical signals throughout the body.
A Low-Voltage Breakthrough
Previous iterations of artificial neurons required significantly higher voltages and power levels, rendering them impractical for direct interaction with biological systems. “Previous versions of artificial neurons used 10 times more voltage – and 100 times more power – than the one we have created,” notes an associate professor of electrical and computer engineering at UMass Amherst and the paper’s senior author.
The newly developed artificial neuron registers a mere 0.1 volts, aligning closely with the electrical activity of natural neurons. This low-voltage operation is crucial for enabling seamless communication between artificial and biological systems.
Applications Beyond Energy Efficiency
The implications of this innovation extend far beyond reduced power consumption.The team envisions a future where computers are redesigned based on bio-inspired principles, leading to dramatically more efficient systems. Moreover,the low-voltage neuron could revolutionize wearable electronics,eliminating the need for power-amplifying circuitry.
“We currently have all kinds of wearable electronic sensing systems,” says the senior author,”but they are comparatively clunky and inefficient. Every time they sense a signal from our body,they have to electrically amplify it so that a computer can analyze it. That intermediate step of amplification increases both power consumption and the circuit’s complexity, but sensors built with our low-voltage neurons could do without any amplification at all.”
Harnessing the Power of Bacteria
The key to this breakthrough lies in a protein nanowire synthesized from Geobacter sulfurreducens, a bacterium renowned for its ability to produce electricity. The research team has previously utilized these nanowires to create a range of innovative devices, including a sweat-powered biofilm for personal electronics, an “electronic nose” capable of detecting disease, and a device that can harvest electricity from the atmosphere.
This research was supported by the Army Research Office, the U.S. National Science Foundation, the national Institutes of Health and the Alfred P. Sloan Foundation, underscoring the broad interest in this promising technology. The development of this bio-inspired neuron marks a pivotal moment in the pursuit of sustainable and efficient computing, bringing us closer to a future where technology seamlessly integrates with the natural world.
Related reading
